© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18044
    Prev
    Next
    INDEX
    Explanations

    printable, How To, ice machine

    np_acts-logits-general · gemini-2.5-flash-lite

    request requires

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hamstring
    0.49
    了两
    0.45
     malonyl
    0.45
     spacers
    0.45
     amni
    0.45
    ponin
    0.44
     passivation
    0.44
    ]]).
    0.43
     placenta
    0.43
     hydrazine
    0.42
    POSITIVE LOGITS
     Degree
    0.50
     Conexion
    0.50
     Is
    0.44
     フェ
    0.43
    bc
    0.43
    "'
    0.43
    abot
    0.41
    anaa
    0.41
    ende
    0.41
     Само
    0.41
    Activations Density 0.001%

    No Known Activations